INDEX

Explanations

keywords related to projects or initiatives

oai_token-act-pair · gpt-3.5-turbo

occurrences of Pokémon characteristics and types

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

•test_feats

No Comments

Negative Logits

 Incarn

-0.59

 Blossom

-0.54

 Jagu

-0.52

beh

-0.51

 seiz

-0.51

 lowly

-0.51

 aforementioned

-0.51

 prest

-0.51

elfth

-0.50

 Drake

-0.49

POSITIVE LOGITS

=\"

0.64

coins

0.61

 greets

0.60

ishes

0.59

lishes

0.57

 awaits

0.57

 returns

0.57

poses

0.57

="

0.56

orts

0.56

Activations Density 0.216%

keywords related to projects or initiatives

occurrences of Pokémon characteristics and types

No Comments

No Known Activations